Engineering Commons^™

Robot Motion Planning In Dynamic Environments, Hao-Tien Lewis Chiang

Computer Science ETDs

Robot motion planning in dynamic environments is critical for many robotic applications, such as self-driving cars, UAVs and service robots operating in changing environments. However, motion planning in dynamic environments is very challenging as this problem has been shown to be NP-Hard and in PSPACE, even in the simplest case. As a result, the lack of safe, efficient planning solutions for real-world robots is one of the biggest obstacles for ubiquitous adoption of robots in everyday life. Specifically, there are four main challenges facing motion planning in dynamic environments: obstacle motion uncertainty, obstacle interaction, complex robot dynamics and noise, and …

A Wearable Mechatronic Device For Hand Tremor Monitoring And Suppression: Development And Evaluation, Yue Zhou

Electronic Thesis and Dissertation Repository

Tremor, one of the most disabling symptoms of Parkinson's disease (PD), significantly affects the quality of life of the individuals who suffer from it. These people live with difficulties with fine motor tasks, such as eating and writing, and suffer from social embarrassment. Traditional medicines are often ineffective, and surgery is highly invasive and risky. The emergence of wearable technology facilitates an externally worn mechatronic tremor suppression device as a potential alternative approach for tremor management. However, no device has been developed for the suppression of finger tremor that has been validated on a human.

It has been reported in …

Reasoning From Point Clouds, Joey Wilson

Computer Engineering

Over the past two years, 3D object detection has been a major area of focus across industry and academia. This is primarily due to the difficulty of learning data from point clouds. While camera images are fixed size and can therefore be easily trained on using convolution, point clouds are unstructured series of points in three dimensions. Therefore, there is no fixed number of features, or a structure to run convolution on. Instead, researchers have developed many ways of attempting to learn from this data, however there is no clear consensus on what is the best method, as each has …

Involuntary Signal-Based Grounding Of Civilian Unmanned Aerial Systems (Uas) In Civilian Airspace, Keith Conley

Master's Theses

This thesis investigates the involuntary signal-based grounding of civilian unmanned aerial systems (UAS) in unauthorized air spaces. The technique proposed here will forcibly land unauthorized UAS in a given area in such a way that the UAS will not be harmed, and the pilot cannot stop the landing. The technique will not involuntarily ground authorized drones which will be determined prior to the landing. Unauthorized airspaces include military bases, university campuses, areas affected by a natural disaster, and stadiums for public events. This thesis proposes an early prototype of a hardware-based signal based involuntary grounding technique to handle the problem …

Distributed Spatiotemporal Control And Dynamic Information Fusion For Multiagent Systems, Dzung Minh Duc Tran

USF Tampa Graduate Theses and Dissertations

The first objective of this dissertation is to develop novel distributed control architectures allowing spatiotemporal control of multiagent systems as applied to formation control. In addition, its second objective is to introduce distributed estimation frameworks for dynamic information fusion for addressing the heterogeneity in sensor networks.

Changing the spatial and temporal properties of agent teams in a distributed manner and in real-time is an open problem in the control system literature as multiagent systems are often required to complete tasks with ever-increasing complexity in adverse conditions and dynamic environments. Motivated by this standpoint, this dissertation aims to address challenges related …

Audio Beat Detection With Application To Robot Drumming, Michael James Engstrom

Dissertations and Theses

This Drumming Robot thesis demonstrates the design of a robot which can play drums in rhythm to an external audio source. The audio source can be either a pre-recorded .wav file or a live sample .wav file from a microphone. The dominant beats-per-minute (BPM) of the audio would be extracted and the robot would drum in time to the BPM. A Fourier Analysis-based BPM detection algorithm, developed by Eric Scheirer (Tempo and beat analysis of acoustical musical signals)ⁱ was adopted and implemented. In contrast to other popular algorithms, the main advantage of Scheirer's algorithm is it has …

Communication Capability For A Simulation-Based Test And Evaluation Framework For Autonomous Systems, Ntiana Sakioti

Computational Modeling & Simulation Engineering Theses & Dissertations

The design and testing process for collaborative autonomous systems can be extremely complex and time-consuming, so it is advantageous to begin testing early in the design. A Test & Evaluation (T&E) Framework was previously developed to enable the testing of autonomous software at various levels of mixed reality. The Framework assumes a modular approach to autonomous software development, which introduces the possibility that components are not in the same stage of development. The T&E Framework allows testing to begin early in a simulated environment, with the autonomous software methodically migrating from virtual to augmented to physical environments as component development …

An Application Of Sliding Mode Control To Model-Based Reinforcement Learning, Aaron Thomas Parisi

Master's Theses

The state-of-art model-free reinforcement learning algorithms can generate admissible controls for complicated systems with no prior knowledge of the system dynamics, so long as sufficient (oftentimes millions) of samples are available from the environ- ment. On the other hand, model-based reinforcement learning approaches seek to leverage known optimal or robust control to reinforcement learning tasks by mod- elling the system dynamics and applying well established control algorithms to the system model. Sliding-mode controllers are robust to system disturbance and modelling errors, and have been widely used for high-order nonlinear system control. This thesis studies the application of sliding mode control …

Utilizing Trajectory Optimization In The Training Of Neural Network Controllers, Nicholas Kimball

Master's Theses

Applying reinforcement learning to control systems enables the use of machine learning to develop elegant and efficient control laws. Coupled with the representational power of neural networks, reinforcement learning algorithms can learn complex policies that can be difficult to emulate using traditional control system design approaches. In this thesis, three different model-free reinforcement learning algorithms, including Monte Carlo Control, REINFORCE with baseline, and Guided Policy Search are compared in simulated, continuous action-space environments. The results show that the Guided Policy Search algorithm is able to learn a desired control policy much faster than the other algorithms. In the inverted pendulum …

Optimal Sampling Paths For Autonomous Vehicles In Uncertain Ocean Flows, Andrew J. De Stefan

Dissertations

Despite an extensive history of oceanic observation, researchers have only begun to build a complete picture of oceanic currents. Sparsity of instrumentation has created the need to maximize the information extracted from every source of data in building this picture. Within the last few decades, autonomous vehicles, or AVs, have been employed as tools to aid in this research initiative. Unmanned and self-propelled, AVs are capable of spending weeks, if not months, exploring and monitoring the oceans. However, the quality of data acquired by these vehicles is highly dependent on the paths along which they collect their observational data. The …

Design Of A Canine Inspired Quadruped Robot As A Platform For Synthetic Neural Network Control, Cody Warren Scharzenberger

Dissertations and Theses

Legged locomotion is a feat ubiquitous throughout the animal kingdom, but modern robots still fall far short of similar achievements. This paper presents the design of a canine-inspired quadruped robot named DoggyDeux as a platform for synthetic neural network (SNN) research that may be one avenue for robots to attain animal-like agility and adaptability. DoggyDeux features a fully 3D printed frame, 24 braided pneumatic actuators (BPAs) that drive four 3-DOF limbs in antagonistic extensor-flexor pairs, and an electrical system that allows it to respond to commands from a SNN comprised of central pattern generators (CPGs). Compared to the previous version …

An Efficient Multiple-Place Foraging Algorithm For Scalable Robot Swarms, Qi Lu

Computer Science ETDs

Searching and collecting multiple resources from large unmapped environments is an important challenge. It is particularly difficult given limited time, a large search area and incomplete data about the environment. This search task is an abstraction of many real-world applications such as search and rescue, hazardous material clean-up, and space exploration. The collective foraging behavior of robot swarms is an effective approach for this task. In our work, individual robots have limited sensing and communication range (like ants), but they are organized and work together to complete foraging tasks collectively. An efficient foraging algorithm coordinates robots to search and collect …

Nonlinear Attitude And Pose Filters With Superior Convergence Properties, Hashim Abdellah Hashim Mohamed

Electronic Thesis and Dissertation Repository

In this thesis, several deterministic and stochastic attitude filtering solutions on the special orthogonal group SO(3) are proposed. Firstly, the attitude estimation problem is approached on the basis of nonlinear deterministic filters on SO(3) with guaranteed transient and steady-state measures. The second solution to the attitude estimation problem considers nonlinear stochastic filters on SO(3) with superior convergence properties with two filters being developed in the sense of Ito, and one in the sense of Stratonovich.

This thesis also presents several deterministic and stochastic pose filtering solutions developed on the special Euclidean group SE(3). The first solution includes two nonlinear deterministic …

A Low-Cost Experimental Testbed For Multi-Agent System Coordination Control, Victor Fernandez-Kim

LSU Master's Theses

A multi-agent system can be defined as a coordinated network of mobile, physical agents that execute complex tasks beyond their individual capabilities. Observations of biological multi-agent systems in nature reveal that these ``super-organisms” accomplish large scale tasks by leveraging the inherent advantages of a coordinated group. With this in mind, such systems have the potential to positively impact a wide variety of engineering applications (e.g. surveillance, self-driving cars, and mobile sensor networks). The current state of research in the area of multi-agent systems is quickly evolving from the theoretical development of coordination control algorithms and their computer simulations to experimental …

Weight Controlled Electric Skateboard, Zachary Barram, Carson Bertozzi, Vishnu Dodballapur

Computer Engineering

Technology and the way that humans interact is becoming more vital and omnipresent with every passing day. However, human interface device designers suffer from the increasingly popular “designed for me or people like me” syndrome. This design philosophy inherently limits accessibility and usability of technology to those like the designer. This places severe limits of usability to those who are not fully able as well as leaves non-traditional human interface devices unexplored. This project set out to explore a previously uncharted human interface device, on an electric skateboard, and compare it send user experience with industry leading human interface devices.

Labeling Paths With Convolutional Neural Networks, Sean Wallace, Kyle Wuerch

Computer Engineering

With the increasing development of autonomous vehicles, being able to detect driveable paths in arbitrary environments has become a prevalent problem in multiple industries. This project explores a technique which utilizes a discretized output map that is used to color an image based on the confidence that each block is a driveable path. This was done using a generalized convolutional neural network that was trained on a set of 3000 images taken from the perspective of a robot along with matching masks marking which portion of the image was a driveable path. The techniques used allowed for a labeling accuracy …

The Soul Annoyed Robot: A Senior Project Report, Dayton Andrew Muxlow, Christian Johansen

Computer Engineering

Our goal for this senior project was to create a competitive robot designed to com- pete in Roborodentia 2019. Our project started during the Winter 2019 quarter, and ended with the competition on May 18, 2019. During that time, we developed an accurate solenoid shooting mechanism, an elevated conveyor belt to carry poker chips, and a servo arm to scoop in stacks of poker chips. These hardware compo- nents were attached to a circular differential-drive wooden base designed to be easy to control. We also planned out our match strategy and implemented this strategy with software written in C/Wiring to …

Planr.: Planar Learning Autonomous Navigation Robot, Gabrielle S. Santamorena, Daniel Kasman, Jesus Mercado, Ben Klave, Andrew Weisman, Anthony Fortner

Computer Engineering

PLANR is a self-contained robot capable of mapping a space and generating 2D floor plans of a building while identifying objects of interest. It runs Robot Operating System (ROS) and houses four main hardware components. An Arduino Mega board handles the navigation, while an NVIDIA Jetson TX2, holds most of the processing power and runs ROS. An Orbbec Astra Pro stereoscopic camera is used for recognition of doors, windows and outlets and the RPLiDAR A3 laser scanner is able to give depth for wall detection and dimension measurements. The robot is intended to operate autonomously and without constant human monitoring …

Robot Navigation In Cluttered Environments With Deep Reinforcement Learning, Ryan Weideman

Master's Theses

The application of robotics in cluttered and dynamic environments provides a wealth of challenges. This thesis proposes a deep reinforcement learning based system that determines collision free navigation robot velocities directly from a sequence of depth images and a desired direction of travel. The system is designed such that a real robot could be placed in an unmapped, cluttered environment and be able to navigate in a desired direction with no prior knowledge. Deep Q-learning, coupled with the innovations of double Q-learning and dueling Q-networks, is applied. Two modifications of this architecture are presented to incorporate direction heading information that …

Exploring The Behavior Repertoire Of A Wireless Vibrationally Actuated Tensegrity Robot, Zongliang Ji

Honors Theses

Soft robotics is an emerging field of research due to its potential to explore and operate in unstructured, rugged, and dynamic environments. However, the properties that make soft robots compelling also make them difficult to robustly control. Here at Union, we developed the world’s first wireless soft tensegrity robot. The goal of my thesis is to explore effective and efficient methods to explore the diverse behavior our tensegrity robot. We will achieve that by applying state-of-art machine learning technique and a novelty search algorithm.

Surveying Underwater Shipwrecks With Probabilistic Roadmaps, Amy Jeannette Lewis

Master's Theses

Almost two thirds of the Earth's surface is covered in ocean, and yet, only about 5% of it is mapped. There are an unknown amount of sunken ships, planes, and other artifacts hidden below the sea. Extensive search via boat and a sonar tow fish following a standard lawnmower pattern is used to identify sites of interest. Then, if a site has been determined to potentially be historically significant, the most common next step is a survey by either a human dive team or remotely operated vehicle. These are time consuming, error prone, and potentially dangerous options, but autonomous underwater …

Towards A Prototype Platform For Ros Integrations On A Ground Robot, Taylor Joseph Linville Whitaker

Graduate Theses and Dissertations

The intent of this work was to develop, evaluate, and demonstrate a prototype robot platform on which ROS integrations could be explored. With observations of features and requirements of existing industrial and service mobile ground robots, a platform was designed and outfitted with appropriate components to enable the most common operational-critical functionalities and account for unforeseen components and features. The resulting Arlo Demonstration Robot accommodates basic mapping, localization, and navigation in both two and three-dimensional space as well as additional safety and teleoperation features. The control system is centered around the Zybo Z7 FPGA SoC hosting a custom hardware design. …

Comparison Of Lqr And Lqr-Mrac For Linear Tractor-Trailer Model, Kevin Richard Gasik

Master's Theses

The United States trucking industry is immense. Employing over three million drivers and traveling to every city in the country. Semi-Trucks travel millions of miles each week and encompass roads that civilians travel on. These vehicles should be safe and allow efficient travel for all. Autonomous vehicles have been discussed in controls for many decades. Now fleets of autonomous vehicles are beginning their integration into society. The ability to create an autonomous system requires domain and system specific knowledge. Approaches to implement a fully autonomous vehicle have been developed using different techniques in control systems such as Kalman Filters, Neural …

Modeling Of Complex Parts For Industrial Waterjet Cleaning, Braden James

Graduate Theses and Dissertations

Industrial high-pressure waterjet cleaning is common to many industries. The modeling in this paper functions inside a collaborative robotic framework for high mix, low volume processes where human robot collaboration is beneficial. Automation of pressure washing is desirable for economic and ergonomic reasons. An automated cleaning system needs path simulation and analysis to give the operator insight into the predicted cleaning performance of the system. In this paper, ablation, the removal of a substrate coating by waterjet, is modeled for robotic cleaning operations. The model is designed to work with complex parts often found in spray cleaning operations, namely parts …

Design And Creation Of A System Of Machines To Automate Quality Control Processes For Atms, Miguel D. Pedrozo

Undergraduate Distinction Papers

This project is based around the quality control processes used to test ATMs. Currently, a person will manually run through each function of the ATM in order to find modes of failure. As the case with all repetitive jobs, it is an unwanted task and is simple enough to be automated. The new solution I propose allows for a system of devices to operate the functions of the ATM autonomously with little to no human intervention. Additionally, this solution is more reliable when diagnosing a problem as it will eventually communicate with the ATM directly in a closed loop system …

End-To-End Learning: Using Neural Networks For Vehicle Control And Obstacle Avoidance, Keith Russell

Honors College Theses

End to End learning is a method of deep learning which has been used to great effect to solve complex problems which would normally be performed by humans. Within this thesis, a neural network was created to mimic the steering patterns of humans in highway driving situations. A Turtlebot was used in place of a car and was tested within a laboratory on a closed loop track to drive within the lanes created for it. The network architecture was based on that of Nvidia’s model which was used for predicting steering angles of a vehicle. The network was successfully trained …

Effects Of Control Device And Task Complexity On Performance And Task Shedding During A Robotic Arm Task, Shelby K. Long

Psychology Theses & Dissertations

The use of robotic arms across domains is increasing, but the relationship between control features and performance is not fully understood. The goal of this research was to investigate the difference in task performance when using two different control devices at high and low task complexities when participants can shed tasks to automation. In this experiment, 40 undergraduates (24 females) used two control devices, a Leap Motion controller and an Xbox controller, to teleoperate a robotic arm in a high or low complexity peg placement task. Simultaneously, participants were tasked with scanning images for tanks. During the experiment, participants had …

A Framework For Test & Evaluation Of Autonomous Systems Along The Virtuality-Reality Spectrum, Nathan D. Gonda

Computational Modeling & Simulation Engineering Theses & Dissertations

Test & Evaluation of autonomous vehicles presents a challenge as the vehicles may have emergent behavior and it is frequently difficult to ascertain the reason for software decisions. Current Test & Evaluation approaches for autonomous systems place the vehicles in various operating scenarios to observe their behavior. However, this introduces dependencies between design and development lifecycle of the autonomous software and physical vehicle hardware. Simulation-based testing can alleviate the necessity to have physical hardware; however, it can be costly when transitioning the autonomous software to and from a simulation testing environment. The objective of this thesis is to develop a …

Robotic Motion Generation By Using Spatial-Temporal Patterns From Human Demonstrations, Yongqiang Huang

USF Tampa Graduate Theses and Dissertations

Robots excel in manufacturing facilities because the tasks are repetitive and do not change. However, when the tasks change, which happens in almost all tasks that humans perform daily, such as cutting, pouring, and grasping, etc., robots perform much worse. We aim at teaching robots to perform tasks that are subject to change using demonstrations collected from humans, a problem referred to as learning from demonstration (LfD).

LfD consists of two parts: the data of human demonstrations, and the algorithm that extracts knowledge from the data to perform the same motions. Similarly, this thesis is divided into two parts. The …

Force Feedback And Intelligent Workspace Selection For Legged Locomotion Over Uneven Terrain, John Rippetoe

USF Tampa Graduate Theses and Dissertations

Legged robots present an incredible opportunity for humanity to conduct dangerous operations such as search and rescue, disaster recovery, and planetary exploration without ever placing themselves in harms way. The ability of a leg to more freely dictate its shape, orientation, and length gives it tremendous mobility and adaptability demanded of a system intended for operation outside of a controlled environment. However, one only need look at the average cat, dog, or friendly neighborhood squirrel to understand the immense gap that exists between what is possible of legged systems and their current set of capabilities.

Areas of study relevant to …